qdrant/docs/grpc/docs.md

Protocol Documentation

Table of Contents

• collections.proto

  • AliasDescription

  • AliasOperations

  • BinaryQuantization

  • ChangeAliases

  • CollectionClusterInfoRequest

  • CollectionClusterInfoResponse

  • CollectionConfig

  • CollectionDescription

  • CollectionInfo

  • CollectionInfo.PayloadSchemaEntry

  • CollectionOperationResponse

  • CollectionParams

  • CollectionParamsDiff

  • CreateAlias

  • CreateCollection

  • DeleteAlias

  • DeleteCollection

  • Disabled

  • GetCollectionInfoRequest

  • GetCollectionInfoResponse

  • HnswConfigDiff

  • ListAliasesRequest

  • ListAliasesResponse

  • ListCollectionAliasesRequest

  • ListCollectionsRequest

  • ListCollectionsResponse

  • LocalShardInfo

  • MoveShard

  • OptimizerStatus

  • OptimizersConfigDiff

  • PayloadIndexParams

  • PayloadSchemaInfo

  • ProductQuantization

  • QuantizationConfig

  • QuantizationConfigDiff

  • RemoteShardInfo

  • RenameAlias

  • Replica

  • ScalarQuantization

  • ShardTransferInfo

  • TextIndexParams

  • UpdateCollection

  • UpdateCollectionClusterSetupRequest

  • UpdateCollectionClusterSetupResponse

  • VectorParams

  • VectorParamsDiff

  • VectorParamsDiffMap

  • VectorParamsDiffMap.MapEntry

  • VectorParamsMap

  • VectorParamsMap.MapEntry

  • VectorsConfig

  • VectorsConfigDiff

  • WalConfigDiff

  • CollectionStatus

  • CompressionRatio

  • Distance

  • PayloadSchemaType

  • QuantizationType

  • ReplicaState

  • TokenizerType

• collections_service.proto

  • Collections

• json_with_int.proto

  • ListValue

  • Struct

  • Struct.FieldsEntry

  • Value

  • NullValue

• points.proto

  • BatchResult

  • ClearPayloadPoints

  • Condition

  • CountPoints

  • CountResponse

  • CountResult

  • CreateFieldIndexCollection

  • DeleteFieldIndexCollection

  • DeletePayloadPoints

  • DeletePointVectors

  • DeletePoints

  • FieldCondition

  • Filter

  • GeoBoundingBox

  • GeoPoint

  • GeoPolygon

  • GeoRadius

  • GetPoints

  • GetResponse

  • GroupId

  • GroupsResult

  • HasIdCondition

  • IsEmptyCondition

  • IsNullCondition

  • LookupLocation

  • Match

  • NamedVectors

  • NamedVectors.VectorsEntry

  • NestedCondition

  • PayloadExcludeSelector

  • PayloadIncludeSelector

  • PointGroup

  • PointId

  • PointStruct

  • PointStruct.PayloadEntry

  • PointVectors

  • PointsIdsList

  • PointsOperationResponse

  • PointsSelector

  • PointsUpdateOperation

  • PointsUpdateOperation.DeletePayload

  • PointsUpdateOperation.DeleteVectors

  • PointsUpdateOperation.PointStructList

  • PointsUpdateOperation.SetPayload

  • PointsUpdateOperation.SetPayload.PayloadEntry

  • PointsUpdateOperation.UpdateVectors

  • QuantizationSearchParams

  • Range

  • ReadConsistency

  • RecommendBatchPoints

  • RecommendBatchResponse

  • RecommendGroupsResponse

  • RecommendPointGroups

  • RecommendPoints

  • RecommendResponse

  • RepeatedIntegers

  • RepeatedStrings

  • RetrievedPoint

  • RetrievedPoint.PayloadEntry

  • ScoredPoint

  • ScoredPoint.PayloadEntry

  • ScrollPoints

  • ScrollResponse

  • SearchBatchPoints

  • SearchBatchResponse

  • SearchGroupsResponse

  • SearchParams

  • SearchPointGroups

  • SearchPoints

  • SearchResponse

  • SetPayloadPoints

  • SetPayloadPoints.PayloadEntry

  • UpdateBatchPoints

  • UpdateBatchResponse

  • UpdatePointVectors

  • UpdateResult

  • UpsertPoints

  • ValuesCount

  • Vector

  • Vectors

  • VectorsSelector

  • WithLookup

  • WithPayloadSelector

  • WithVectorsSelector

  • WriteOrdering

  • FieldType

  • ReadConsistencyType

  • UpdateStatus

  • WriteOrderingType

• points_service.proto

  • Points

• qdrant.proto

  • HealthCheckReply

  • HealthCheckRequest

  • Qdrant

• qdrant_internal_service.proto

  • HttpPortRequest

  • HttpPortResponse

  • QdrantInternal

• snapshots_service.proto

  • CreateFullSnapshotRequest

  • CreateSnapshotRequest

  • CreateSnapshotResponse

  • DeleteFullSnapshotRequest

  • DeleteSnapshotRequest

  • DeleteSnapshotResponse

  • ListFullSnapshotsRequest

  • ListSnapshotsRequest

  • ListSnapshotsResponse

  • SnapshotDescription

  • Snapshots

• Scalar Value Types

Top

collections.proto

AliasDescription

Field	Type	Label	Description
alias_name	string		Name of the alias
collection_name	string		Name of the collection

AliasOperations

Field	Type	Label	Description
create_alias	CreateAlias
rename_alias	RenameAlias
delete_alias	DeleteAlias

BinaryQuantization

Field	Type	Label	Description
always_ram	bool	optional	If true - quantized vectors always will be stored in RAM, ignoring the config of main storage

ChangeAliases

Field	Type	Label	Description
actions	AliasOperations	repeated	List of actions
timeout	uint64	optional	Wait timeout for operation commit in seconds, if not specified - default value will be supplied

CollectionClusterInfoRequest

Field	Type	Label	Description
collection_name	string		Name of the collection

CollectionClusterInfoResponse

Field	Type	Label	Description
peer_id	uint64		ID of this peer
shard_count	uint64		Total number of shards
local_shards	LocalShardInfo	repeated	Local shards
remote_shards	RemoteShardInfo	repeated	Remote shards
shard_transfers	ShardTransferInfo	repeated	Shard transfers

CollectionConfig

Field	Type	Label	Description
params	CollectionParams		Collection parameters
hnsw_config	HnswConfigDiff		Configuration of vector index
optimizer_config	OptimizersConfigDiff		Configuration of the optimizers
wal_config	WalConfigDiff		Configuration of the Write-Ahead-Log
quantization_config	QuantizationConfig	optional	Configuration of the vector quantization

CollectionDescription

Field	Type	Label	Description
name	string		Name of the collection

CollectionInfo

Field	Type	Label	Description
status	CollectionStatus		operating condition of the collection
optimizer_status	OptimizerStatus		status of collection optimizers
vectors_count	uint64		number of vectors in the collection
segments_count	uint64		Number of independent segments
config	CollectionConfig		Configuration
payload_schema	CollectionInfo.PayloadSchemaEntry	repeated	Collection data types
points_count	uint64		number of points in the collection
indexed_vectors_count	uint64	optional	number of indexed vectors in the collection.

CollectionInfo.PayloadSchemaEntry

Field	Type	Label	Description
key	string
value	PayloadSchemaInfo

CollectionOperationResponse

Field	Type	Label	Description
result	bool		if operation made changes
time	double		Time spent to process

CollectionParams

Field	Type	Label	Description
shard_number	uint32		Number of shards in collection
on_disk_payload	bool		If true - point's payload will not be stored in memory
vectors_config	VectorsConfig	optional	Configuration for vectors
replication_factor	uint32	optional	Number of replicas of each shard that network tries to maintain
write_consistency_factor	uint32	optional	How many replicas should apply the operation for us to consider it successful

CollectionParamsDiff

Field	Type	Label	Description
replication_factor	uint32	optional	Number of replicas of each shard that network tries to maintain
write_consistency_factor	uint32	optional	How many replicas should apply the operation for us to consider it successful
on_disk_payload	bool	optional	If true - point's payload will not be stored in memory

CreateAlias

Field	Type	Label	Description
collection_name	string		Name of the collection
alias_name	string		New name of the alias

CreateCollection

Field	Type	Label	Description
collection_name	string		Name of the collection
hnsw_config	HnswConfigDiff	optional	Configuration of vector index
wal_config	WalConfigDiff	optional	Configuration of the Write-Ahead-Log
optimizers_config	OptimizersConfigDiff	optional	Configuration of the optimizers
shard_number	uint32	optional	Number of shards in the collection, default is 1 for standalone, otherwise equal to the number of nodes. Minimum is 1
on_disk_payload	bool	optional	If true - point's payload will not be stored in memory
timeout	uint64	optional	Wait timeout for operation commit in seconds, if not specified - default value will be supplied
vectors_config	VectorsConfig	optional	Configuration for vectors
replication_factor	uint32	optional	Number of replicas of each shard that network tries to maintain, default = 1
write_consistency_factor	uint32	optional	How many replicas should apply the operation for us to consider it successful, default = 1
init_from_collection	string	optional	Specify name of the other collection to copy data from
quantization_config	QuantizationConfig	optional	Quantization configuration of vector

DeleteAlias

Field	Type	Label	Description
alias_name	string		Name of the alias

DeleteCollection

Field	Type	Label	Description
collection_name	string		Name of the collection
timeout	uint64	optional	Wait timeout for operation commit in seconds, if not specified - default value will be supplied

Disabled

GetCollectionInfoRequest

Field	Type	Label	Description
collection_name	string		Name of the collection

GetCollectionInfoResponse

Field	Type	Label	Description
result	CollectionInfo
time	double		Time spent to process

HnswConfigDiff

Field	Type	Label	Description
m	uint64	optional	Number of edges per node in the index graph. Larger the value - more accurate the search, more space required.
ef_construct	uint64	optional	Number of neighbours to consider during the index building. Larger the value - more accurate the search, more time required to build the index.
full_scan_threshold	uint64	optional	Minimal size (in KiloBytes) of vectors for additional payload-based indexing. If the payload chunk is smaller than full_scan_threshold additional indexing won't be used - in this case full-scan search should be preferred by query planner and additional indexing is not required. Note: 1 Kb = 1 vector of size 256
max_indexing_threads	uint64	optional	Number of parallel threads used for background index building. If 0 - auto selection.
on_disk	bool	optional	Store HNSW index on disk. If set to false, the index will be stored in RAM.
payload_m	uint64	optional	Number of additional payload-aware links per node in the index graph. If not set - regular M parameter will be used.

ListAliasesRequest

ListAliasesResponse

Field	Type	Label	Description
aliases	AliasDescription	repeated
time	double		Time spent to process

ListCollectionAliasesRequest

Field	Type	Label	Description
collection_name	string		Name of the collection

ListCollectionsRequest

ListCollectionsResponse

Field	Type	Label	Description
collections	CollectionDescription	repeated
time	double		Time spent to process

LocalShardInfo

Field	Type	Label	Description
shard_id	uint32		Local shard id
points_count	uint64		Number of points in the shard
state	ReplicaState		Is replica active

MoveShard

Field	Type	Label	Description
shard_id	uint32		Local shard id
from_peer_id	uint64
to_peer_id	uint64

OptimizerStatus

Field	Type	Label	Description
ok	bool
error	string

OptimizersConfigDiff

Field	Type	Label	Description
deleted_threshold	double	optional	The minimal fraction of deleted vectors in a segment, required to perform segment optimization
vacuum_min_vector_number	uint64	optional	The minimal number of vectors in a segment, required to perform segment optimization
default_segment_number	uint64	optional	Target amount of segments the optimizer will try to keep. Real amount of segments may vary depending on multiple parameters:

• Amount of stored points. - Current write RPS.

It is recommended to select the default number of segments as a factor of the number of search threads, so that each segment would be handled evenly by one of the threads. | | max_segment_size | uint64 | optional | Do not create segments larger this size (in kilobytes). Large segments might require disproportionately long indexation times, therefore it makes sense to limit the size of segments.

If indexing speed is more important - make this parameter lower. If search speed is more important - make this parameter higher. Note: 1Kb = 1 vector of size 256 If not set, will be automatically selected considering the number of available CPUs. | | memmap_threshold | uint64 | optional | Maximum size (in kilobytes) of vectors to store in-memory per segment. Segments larger than this threshold will be stored as read-only memmaped file.

Memmap storage is disabled by default, to enable it, set this threshold to a reasonable value.

To disable memmap storage, set this to 0.

Note: 1Kb = 1 vector of size 256 | | indexing_threshold | uint64 | optional | Maximum size (in kilobytes) of vectors allowed for plain index, exceeding this threshold will enable vector indexing

Default value is 20,000, based on <https://github.com/google-research/google-research/blob/master/scann/docs/algorithms.md>.

To disable vector indexing, set to 0.

Note: 1kB = 1 vector of size 256. | | flush_interval_sec | uint64 | optional | Interval between forced flushes. | | max_optimization_threads | uint64 | optional | Max number of threads, which can be used for optimization. If 0 - NUM_CPU - 1 will be used |

PayloadIndexParams

Field	Type	Label	Description
text_index_params	TextIndexParams		Parameters for text index

PayloadSchemaInfo

Field	Type	Label	Description
data_type	PayloadSchemaType		Field data type
params	PayloadIndexParams	optional	Field index parameters
points	uint64	optional	Number of points indexed within this field indexed

ProductQuantization

Field	Type	Label	Description
compression	CompressionRatio		Compression ratio
always_ram	bool	optional	If true - quantized vectors always will be stored in RAM, ignoring the config of main storage

QuantizationConfig

Field	Type	Label	Description
scalar	ScalarQuantization
product	ProductQuantization
binary	BinaryQuantization

QuantizationConfigDiff

Field	Type	Label	Description
scalar	ScalarQuantization
product	ProductQuantization
disabled	Disabled
binary	BinaryQuantization

RemoteShardInfo

Field	Type	Label	Description
shard_id	uint32		Local shard id
peer_id	uint64		Remote peer id
state	ReplicaState		Is replica active

RenameAlias

Field	Type	Label	Description
old_alias_name	string		Name of the alias to rename
new_alias_name	string		Name of the alias

Replica

Field	Type	Label	Description
shard_id	uint32
peer_id	uint64

ScalarQuantization

Field	Type	Label	Description
type	QuantizationType		Type of quantization
quantile	float	optional	Number of bits to use for quantization
always_ram	bool	optional	If true - quantized vectors always will be stored in RAM, ignoring the config of main storage

ShardTransferInfo

Field	Type	Label	Description
shard_id	uint32		Local shard id
from	uint64
to	uint64
sync	bool		If true transfer is a synchronization of a replicas; If false transfer is a moving of a shard from one peer to another

TextIndexParams

Field	Type	Label	Description
tokenizer	TokenizerType		Tokenizer type
lowercase	bool	optional	If true - all tokens will be lowercase
min_token_len	uint64	optional	Minimal token length
max_token_len	uint64	optional	Maximal token length

UpdateCollection

Field	Type	Label	Description
collection_name	string		Name of the collection
optimizers_config	OptimizersConfigDiff	optional	New configuration parameters for the collection. This operation is blocking, it will only proceed once all current optimizations are complete
timeout	uint64	optional	Wait timeout for operation commit in seconds if blocking, if not specified - default value will be supplied
params	CollectionParamsDiff	optional	New configuration parameters for the collection
hnsw_config	HnswConfigDiff	optional	New HNSW parameters for the collection index
vectors_config	VectorsConfigDiff	optional	New vector parameters
quantization_config	QuantizationConfigDiff	optional	Quantization configuration of vector

UpdateCollectionClusterSetupRequest

Field	Type	Label	Description
collection_name	string		Name of the collection
move_shard	MoveShard
replicate_shard	MoveShard
abort_transfer	MoveShard
drop_replica	Replica
timeout	uint64	optional	Wait timeout for operation commit in seconds, if not specified - default value will be supplied

UpdateCollectionClusterSetupResponse

Field	Type	Label	Description
result	bool

VectorParams

Field	Type	Label	Description
size	uint64		Size of the vectors
distance	Distance		Distance function used for comparing vectors
hnsw_config	HnswConfigDiff	optional	Configuration of vector HNSW graph. If omitted - the collection configuration will be used
quantization_config	QuantizationConfig	optional	Configuration of vector quantization config. If omitted - the collection configuration will be used
on_disk	bool	optional	If true - serve vectors from disk. If set to false, the vectors will be loaded in RAM.

VectorParamsDiff

Field	Type	Label	Description
hnsw_config	HnswConfigDiff	optional	Update params for HNSW index. If empty object - it will be unset
quantization_config	QuantizationConfigDiff	optional	Update quantization params. If none - it is left unchanged.
on_disk	bool	optional	If true - serve vectors from disk. If set to false, the vectors will be loaded in RAM.

VectorParamsDiffMap

Field	Type	Label	Description
map	VectorParamsDiffMap.MapEntry	repeated

VectorParamsDiffMap.MapEntry

Field	Type	Label	Description
key	string
value	VectorParamsDiff

VectorParamsMap

Field	Type	Label	Description
map	VectorParamsMap.MapEntry	repeated

VectorParamsMap.MapEntry

Field	Type	Label	Description
key	string
value	VectorParams

VectorsConfig

Field	Type	Label	Description
params	VectorParams
params_map	VectorParamsMap

VectorsConfigDiff

Field	Type	Label	Description
params	VectorParamsDiff
params_map	VectorParamsDiffMap

WalConfigDiff

Field	Type	Label	Description
wal_capacity_mb	uint64	optional	Size of a single WAL block file
wal_segments_ahead	uint64	optional	Number of segments to create in advance

CollectionStatus

Name	Number	Description
UnknownCollectionStatus	0
Green	1	All segments are ready
Yellow	2	Optimization in process
Red	3	Something went wrong

CompressionRatio

Name	Number	Description
x4	0
x8	1
x16	2
x32	3
x64	4

Distance

Name	Number	Description
UnknownDistance	0
Cosine	1
Euclid	2
Dot	3

PayloadSchemaType

Name	Number	Description
UnknownType	0
Keyword	1
Integer	2
Float	3
Geo	4
Text	5
Bool	6

QuantizationType

Name	Number	Description
UnknownQuantization	0
Int8	1

ReplicaState

Name	Number	Description
Active	0	Active and sound
Dead	1	Failed for some reason
Partial	2	The shard is partially loaded and is currently receiving data from other shards
Initializing	3	Collection is being created
Listener	4	A shard which receives data, but is not used for search; Useful for backup shards

TokenizerType

Name	Number	Description
Unknown	0
Prefix	1
Whitespace	2
Word	3
Multilingual	4

Top

collections_service.proto

Collections

Method Name	Request Type	Response Type	Description
Get	GetCollectionInfoRequest	GetCollectionInfoResponse	Get detailed information about specified existing collection
List	ListCollectionsRequest	ListCollectionsResponse	Get list name of all existing collections
Create	CreateCollection	CollectionOperationResponse	Create new collection with given parameters
Update	UpdateCollection	CollectionOperationResponse	Update parameters of the existing collection
Delete	DeleteCollection	CollectionOperationResponse	Drop collection and all associated data
UpdateAliases	ChangeAliases	CollectionOperationResponse	Update Aliases of the existing collection
ListCollectionAliases	ListCollectionAliasesRequest	ListAliasesResponse	Get list of all aliases for a collection
ListAliases	ListAliasesRequest	ListAliasesResponse	Get list of all aliases for all existing collections
CollectionClusterInfo	CollectionClusterInfoRequest	CollectionClusterInfoResponse	Get cluster information for a collection
UpdateCollectionClusterSetup	UpdateCollectionClusterSetupRequest	UpdateCollectionClusterSetupResponse	Update cluster setup for a collection

Top

json_with_int.proto

ListValue

ListValue is a wrapper around a repeated field of values.

The JSON representation for ListValue is a JSON array.

Field	Type	Label	Description
values	Value	repeated	Repeated field of dynamically typed values.

Struct

Struct represents a structured data value, consisting of fields which map to dynamically typed values. In some languages, Struct might be supported by a native representation. For example, in scripting languages like JS a struct is represented as an object. The details of that representation are described together with the proto support for the language.

The JSON representation for Struct is a JSON object.

Field	Type	Label	Description
fields	Struct.FieldsEntry	repeated	Unordered map of dynamically typed values.

Struct.FieldsEntry

Field	Type	Label	Description
key	string
value	Value

Value

Value represents a dynamically typed value which can be either null, a number, a string, a boolean, a recursive struct value, or a list of values. A producer of value is expected to set one of those variants, absence of any variant indicates an error.

The JSON representation for Value is a JSON value.

Field	Type	Label	Description
null_value	NullValue		Represents a null value.
double_value	double		Represents a double value.
integer_value	int64		Represents an integer value
string_value	string		Represents a string value.
bool_value	bool		Represents a boolean value.
struct_value	Struct		Represents a structured value.
list_value	ListValue		Represents a repeated Value.

NullValue

NullValue is a singleton enumeration to represent the null value for the Value type union.

The JSON representation for NullValue is JSON null.

Name	Number	Description
NULL_VALUE	0	Null value.

Top

points.proto

BatchResult

Field	Type	Label	Description
result	ScoredPoint	repeated

ClearPayloadPoints

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
points	PointsSelector		Affected points
ordering	WriteOrdering	optional	Write ordering guarantees

Condition

Field	Type	Label	Description
field	FieldCondition
is_empty	IsEmptyCondition
has_id	HasIdCondition
filter	Filter
is_null	IsNullCondition
nested	NestedCondition

CountPoints

Field	Type	Label	Description
collection_name	string		name of the collection
filter	Filter		Filter conditions - return only those points that satisfy the specified conditions
exact	bool	optional	If true - return exact count, if false - return approximate count

CountResponse

Field	Type	Label	Description
result	CountResult
time	double		Time spent to process

CountResult

Field	Type	Label	Description
count	uint64

CreateFieldIndexCollection

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
field_name	string		Field name to index
field_type	FieldType	optional	Field type.
field_index_params	PayloadIndexParams	optional	Payload index params.
ordering	WriteOrdering	optional	Write ordering guarantees

DeleteFieldIndexCollection

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
field_name	string		Field name to delete
ordering	WriteOrdering	optional	Write ordering guarantees

DeletePayloadPoints

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
keys	string	repeated	List of keys to delete
points_selector	PointsSelector	optional	Affected points
ordering	WriteOrdering	optional	Write ordering guarantees

DeletePointVectors

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
points_selector	PointsSelector		Affected points
vectors	VectorsSelector		List of vector names to delete
ordering	WriteOrdering	optional	Write ordering guarantees

DeletePoints

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
points	PointsSelector		Affected points
ordering	WriteOrdering	optional	Write ordering guarantees

FieldCondition

Field	Type	Label	Description
key	string
match	Match		Check if point has field with a given value
range	Range		Check if points value lies in a given range
geo_bounding_box	GeoBoundingBox		Check if points geolocation lies in a given area
geo_radius	GeoRadius		Check if geo point is within a given radius
values_count	ValuesCount		Check number of values for a specific field

Filter

Field	Type	Label	Description
should	Condition	repeated	At least one of those conditions should match
must	Condition	repeated	All conditions must match
must_not	Condition	repeated	All conditions must NOT match

GeoBoundingBox

Field	Type	Label	Description
top_left	GeoPoint		north-west corner
bottom_right	GeoPoint		south-east corner

GeoPoint

Field	Type	Label	Description
lon	double
lat	double

GeoPolygon

Field	Type	Label	Description
points	GeoPoint	repeated	Ordered list of coordinates representing the vertices of a polygon. The minimum size is 4, and the first coordinate and the last coordinate should be the same to form a closed polygon.

GeoRadius

Field	Type	Label	Description
center	GeoPoint		Center of the circle
radius	float		In meters

GetPoints

Field	Type	Label	Description
collection_name	string		name of the collection
ids	PointId	repeated	List of points to retrieve
with_payload	WithPayloadSelector		Options for specifying which payload to include or not
with_vectors	WithVectorsSelector	optional	Options for specifying which vectors to include into response
read_consistency	ReadConsistency	optional	Options for specifying read consistency guarantees

GetResponse

Field	Type	Label	Description
result	RetrievedPoint	repeated
time	double		Time spent to process

GroupId

Field	Type	Label	Description
unsigned_value	uint64		Represents a double value.
integer_value	int64		Represents an integer value
string_value	string		Represents a string value.

GroupsResult

Field	Type	Label	Description
groups	PointGroup	repeated	Groups

HasIdCondition

Field	Type	Label	Description
has_id	PointId	repeated

IsEmptyCondition

Field	Type	Label	Description
key	string

IsNullCondition

Field	Type	Label	Description
key	string

LookupLocation

Field	Type	Label	Description
collection_name	string
vector_name	string	optional	Which vector to use for search, if not specified - use default vector

Match

Field	Type	Label	Description
keyword	string		Match string keyword
integer	int64		Match integer
boolean	bool		Match boolean
text	string		Match text
keywords	RepeatedStrings		Match multiple keywords
integers	RepeatedIntegers		Match multiple integers
except_integers	RepeatedIntegers		Match any other value except those integers
except_keywords	RepeatedStrings		Match any other value except those keywords

NamedVectors

Field	Type	Label	Description
vectors	NamedVectors.VectorsEntry	repeated

NamedVectors.VectorsEntry

Field	Type	Label	Description
key	string
value	Vector

NestedCondition

Field	Type	Label	Description
key	string		Path to nested object
filter	Filter		Filter condition

PayloadExcludeSelector

Field	Type	Label	Description
fields	string	repeated	List of payload keys to exclude from the result

PayloadIncludeSelector

Field	Type	Label	Description
fields	string	repeated	List of payload keys to include into result

PointGroup

Field	Type	Label	Description
id	GroupId		Group id
hits	ScoredPoint	repeated	Points in the group
lookup	RetrievedPoint		Point(s) from the lookup collection that matches the group id

PointId

Field	Type	Label	Description
num	uint64		Numerical ID of the point
uuid	string		UUID

PointStruct

Field	Type	Label	Description
id	PointId
payload	PointStruct.PayloadEntry	repeated
vectors	Vectors	optional

PointStruct.PayloadEntry

Field	Type	Label	Description
key	string
value	Value

PointVectors

Field	Type	Label	Description
id	PointId		ID to update vectors for
vectors	Vectors		Named vectors to update, leave others intact

PointsIdsList

Field	Type	Label	Description
ids	PointId	repeated

PointsOperationResponse

Field	Type	Label	Description
result	UpdateResult
time	double		Time spent to process

PointsSelector

Field	Type	Label	Description
points	PointsIdsList
filter	Filter

PointsUpdateOperation

Field	Type	Label	Description
upsert	PointsUpdateOperation.PointStructList
delete	PointsSelector
set_payload	PointsUpdateOperation.SetPayload
overwrite_payload	PointsUpdateOperation.SetPayload
delete_payload	PointsUpdateOperation.DeletePayload
clear_payload	PointsSelector
update_vectors	PointsUpdateOperation.UpdateVectors
delete_vectors	PointsUpdateOperation.DeleteVectors

PointsUpdateOperation.DeletePayload

Field	Type	Label	Description
keys	string	repeated
points_selector	PointsSelector	optional	Affected points

PointsUpdateOperation.DeleteVectors

Field	Type	Label	Description
points_selector	PointsSelector		Affected points
vectors	VectorsSelector		List of vector names to delete

PointsUpdateOperation.PointStructList

Field	Type	Label	Description
points	PointStruct	repeated

PointsUpdateOperation.SetPayload

Field	Type	Label	Description
payload	PointsUpdateOperation.SetPayload.PayloadEntry	repeated
points_selector	PointsSelector	optional	Affected points

PointsUpdateOperation.SetPayload.PayloadEntry

Field	Type	Label	Description
key	string
value	Value

PointsUpdateOperation.UpdateVectors

Field	Type	Label	Description
points	PointVectors	repeated	List of points and vectors to update

QuantizationSearchParams

Field	Type	Label	Description
ignore	bool	optional	If set to true, search will ignore quantized vector data
rescore	bool	optional	If true, use original vectors to re-score top-k results. Default is true.
oversampling	double	optional	Oversampling factor for quantization.

Defines how many extra vectors should be pre-selected using quantized index, and then re-scored using original vectors.

For example, if oversampling is 2.4 and limit is 100, then 240 vectors will be pre-selected using quantized index, and then top-100 will be returned after re-scoring. |

Range

Field	Type	Label	Description
lt	double	optional
gt	double	optional
gte	double	optional
lte	double	optional

ReadConsistency

Field	Type	Label	Description
type	ReadConsistencyType		Common read consistency configurations
factor	uint64		Send request to a specified number of nodes, and return points which are present on all of them

RecommendBatchPoints

Field	Type	Label	Description
collection_name	string		Name of the collection
recommend_points	RecommendPoints	repeated
read_consistency	ReadConsistency	optional	Options for specifying read consistency guarantees

RecommendBatchResponse

Field	Type	Label	Description
result	BatchResult	repeated
time	double		Time spent to process

RecommendGroupsResponse

Field	Type	Label	Description
result	GroupsResult
time	double		Time spent to process

RecommendPointGroups

Field	Type	Label	Description
collection_name	string		Name of the collection
positive	PointId	repeated	Look for vectors closest to those
negative	PointId	repeated	Try to avoid vectors like this
filter	Filter		Filter conditions - return only those points that satisfy the specified conditions
limit	uint32		Max number of groups in result
with_payload	WithPayloadSelector		Options for specifying which payload to include or not
params	SearchParams		Search config
score_threshold	float	optional	If provided - cut off results with worse scores
using	string	optional	Define which vector to use for recommendation, if not specified - default vector
with_vectors	WithVectorsSelector	optional	Options for specifying which vectors to include into response
lookup_from	LookupLocation	optional	Name of the collection to use for points lookup, if not specified - use current collection
group_by	string		Payload field to group by, must be a string or number field. If there are multiple values for the field, all of them will be used. One point can be in multiple groups.
group_size	uint32		Maximum amount of points to return per group
read_consistency	ReadConsistency	optional	Options for specifying read consistency guarantees
with_lookup	WithLookup	optional	Options for specifying how to use the group id to lookup points in another collection

RecommendPoints

Field	Type	Label	Description
collection_name	string		name of the collection
positive	PointId	repeated	Look for vectors closest to those
negative	PointId	repeated	Try to avoid vectors like this
filter	Filter		Filter conditions - return only those points that satisfy the specified conditions
limit	uint64		Max number of result
with_payload	WithPayloadSelector		Options for specifying which payload to include or not
params	SearchParams		Search config
score_threshold	float	optional	If provided - cut off results with worse scores
offset	uint64	optional	Offset of the result
using	string	optional	Define which vector to use for recommendation, if not specified - default vector
with_vectors	WithVectorsSelector	optional	Options for specifying which vectors to include into response
lookup_from	LookupLocation	optional	Name of the collection to use for points lookup, if not specified - use current collection
read_consistency	ReadConsistency	optional	Options for specifying read consistency guarantees

RecommendResponse

Field	Type	Label	Description
result	ScoredPoint	repeated
time	double		Time spent to process

RepeatedIntegers

Field	Type	Label	Description
integers	int64	repeated

RepeatedStrings

Field	Type	Label	Description
strings	string	repeated

RetrievedPoint

Field	Type	Label	Description
id	PointId
payload	RetrievedPoint.PayloadEntry	repeated
vectors	Vectors	optional

RetrievedPoint.PayloadEntry

Field	Type	Label	Description
key	string
value	Value

ScoredPoint

Field	Type	Label	Description
id	PointId		Point id
payload	ScoredPoint.PayloadEntry	repeated	Payload
score	float		Similarity score
version	uint64		Last update operation applied to this point
vectors	Vectors	optional	Vectors to search

ScoredPoint.PayloadEntry

Field	Type	Label	Description
key	string
value	Value

ScrollPoints

Field	Type	Label	Description
collection_name	string
filter	Filter		Filter conditions - return only those points that satisfy the specified conditions
offset	PointId	optional	Start with this ID
limit	uint32	optional	Max number of result
with_payload	WithPayloadSelector		Options for specifying which payload to include or not
with_vectors	WithVectorsSelector	optional	Options for specifying which vectors to include into response
read_consistency	ReadConsistency	optional	Options for specifying read consistency guarantees

ScrollResponse

Field	Type	Label	Description
next_page_offset	PointId	optional	Use this offset for the next query
result	RetrievedPoint	repeated
time	double		Time spent to process

SearchBatchPoints

Field	Type	Label	Description
collection_name	string		Name of the collection
search_points	SearchPoints	repeated
read_consistency	ReadConsistency	optional	Options for specifying read consistency guarantees

SearchBatchResponse

Field	Type	Label	Description
result	BatchResult	repeated
time	double		Time spent to process

SearchGroupsResponse

Field	Type	Label	Description
result	GroupsResult
time	double		Time spent to process

SearchParams

Field	Type	Label	Description
hnsw_ef	uint64	optional	Params relevant to HNSW index. Size of the beam in a beam-search. Larger the value - more accurate the result, more time required for search.
exact	bool	optional	Search without approximation. If set to true, search may run long but with exact results.
quantization	QuantizationSearchParams	optional	If set to true, search will ignore quantized vector data
indexed_only	bool	optional	If enabled, the engine will only perform search among indexed or small segments. Using this option prevents slow searches in case of delayed index, but does not guarantee that all uploaded vectors will be included in search results

SearchPointGroups

Field	Type	Label	Description
collection_name	string		Name of the collection
vector	float	repeated	Vector to compare against
filter	Filter		Filter conditions - return only those points that satisfy the specified conditions
limit	uint32		Max number of result
with_payload	WithPayloadSelector		Options for specifying which payload to include or not
params	SearchParams		Search config
score_threshold	float	optional	If provided - cut off results with worse scores
vector_name	string	optional	Which vector to use for search, if not specified - use default vector
with_vectors	WithVectorsSelector	optional	Options for specifying which vectors to include into response
group_by	string		Payload field to group by, must be a string or number field. If there are multiple values for the field, all of them will be used. One point can be in multiple groups.
group_size	uint32		Maximum amount of points to return per group
read_consistency	ReadConsistency	optional	Options for specifying read consistency guarantees
with_lookup	WithLookup	optional	Options for specifying how to use the group id to lookup points in another collection

SearchPoints

Field	Type	Label	Description
collection_name	string		name of the collection
vector	float	repeated	vector
filter	Filter		Filter conditions - return only those points that satisfy the specified conditions
limit	uint64		Max number of result
with_payload	WithPayloadSelector		Options for specifying which payload to include or not
params	SearchParams		Search config
score_threshold	float	optional	If provided - cut off results with worse scores
offset	uint64	optional	Offset of the result
vector_name	string	optional	Which vector to use for search, if not specified - use default vector
with_vectors	WithVectorsSelector	optional	Options for specifying which vectors to include into response
read_consistency	ReadConsistency	optional	Options for specifying read consistency guarantees

SearchResponse

Field	Type	Label	Description
result	ScoredPoint	repeated
time	double		Time spent to process

SetPayloadPoints

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
payload	SetPayloadPoints.PayloadEntry	repeated	New payload values
points_selector	PointsSelector	optional	Affected points
ordering	WriteOrdering	optional	Write ordering guarantees

SetPayloadPoints.PayloadEntry

Field	Type	Label	Description
key	string
value	Value

UpdateBatchPoints

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
operations	PointsUpdateOperation	repeated
ordering	WriteOrdering	optional	Write ordering guarantees

UpdateBatchResponse

Field	Type	Label	Description
result	UpdateResult	repeated
time	double		Time spent to process

UpdatePointVectors

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
points	PointVectors	repeated	List of points and vectors to update
ordering	WriteOrdering	optional	Write ordering guarantees

UpdateResult

Field	Type	Label	Description
operation_id	uint64		Number of operation
status	UpdateStatus		Operation status

UpsertPoints

Field	Type	Label	Description
collection_name	string		name of the collection
wait	bool	optional	Wait until the changes have been applied?
points	PointStruct	repeated
ordering	WriteOrdering	optional	Write ordering guarantees

ValuesCount

Field	Type	Label	Description
lt	uint64	optional
gt	uint64	optional
gte	uint64	optional
lte	uint64	optional

Vector

Field	Type	Label	Description
data	float	repeated

Vectors

Field	Type	Label	Description
vector	Vector
vectors	NamedVectors

VectorsSelector

Field	Type	Label	Description
names	string	repeated	List of vectors to include into result

WithLookup

Field	Type	Label	Description
collection	string		Name of the collection to use for points lookup
with_payload	WithPayloadSelector	optional	Options for specifying which payload to include (or not)
with_vectors	WithVectorsSelector	optional	Options for specifying which vectors to include (or not)

WithPayloadSelector

Field	Type	Label	Description
enable	bool		If true - return all payload, if false - none
include	PayloadIncludeSelector
exclude	PayloadExcludeSelector

WithVectorsSelector

Field	Type	Label	Description
enable	bool		If true - return all vectors, if false - none
include	VectorsSelector		List of payload keys to include into result

WriteOrdering

Field	Type	Label	Description
type	WriteOrderingType		Write ordering guarantees

FieldType

Name	Number	Description
FieldTypeKeyword	0
FieldTypeInteger	1
FieldTypeFloat	2
FieldTypeGeo	3
FieldTypeText	4
FieldTypeBool	5

ReadConsistencyType

Name	Number	Description
All	0	Send request to all nodes and return points which are present on all of them
Majority	1	Send requests to all nodes and return points which are present on majority of them
Quorum	2	Send requests to half + 1 nodes, return points which are present on all of them

UpdateStatus

Name	Number	Description
UnknownUpdateStatus	0
Acknowledged	1	Update is received, but not processed yet
Completed	2	Update is applied and ready for search

WriteOrderingType

Name	Number	Description
Weak	0	Write operations may be reordered, works faster, default
Medium	1	Write operations go through dynamically selected leader, may be inconsistent for a short period of time in case of leader change
Strong	2	Write operations go through the permanent leader, consistent, but may be unavailable if leader is down

Top

points_service.proto

Points

Method Name	Request Type	Response Type	Description
Upsert	UpsertPoints	PointsOperationResponse	Perform insert + updates on points. If a point with a given ID already exists - it will be overwritten.
Delete	DeletePoints	PointsOperationResponse	Delete points
Get	GetPoints	GetResponse	Retrieve points
UpdateVectors	UpdatePointVectors	PointsOperationResponse	Update named vectors for point
DeleteVectors	DeletePointVectors	PointsOperationResponse	Delete named vectors for points
SetPayload	SetPayloadPoints	PointsOperationResponse	Set payload for points
OverwritePayload	SetPayloadPoints	PointsOperationResponse	Overwrite payload for points
DeletePayload	DeletePayloadPoints	PointsOperationResponse	Delete specified key payload for points
ClearPayload	ClearPayloadPoints	PointsOperationResponse	Remove all payload for specified points
CreateFieldIndex	CreateFieldIndexCollection	PointsOperationResponse	Create index for field in collection
DeleteFieldIndex	DeleteFieldIndexCollection	PointsOperationResponse	Delete field index for collection
Search	SearchPoints	SearchResponse	Retrieve closest points based on vector similarity and given filtering conditions
SearchBatch	SearchBatchPoints	SearchBatchResponse	Retrieve closest points based on vector similarity and given filtering conditions
SearchGroups	SearchPointGroups	SearchGroupsResponse	Retrieve closest points based on vector similarity and given filtering conditions, grouped by a given field
Scroll	ScrollPoints	ScrollResponse	Iterate over all or filtered points points
Recommend	RecommendPoints	RecommendResponse	Look for the points which are closer to stored positive examples and at the same time further to negative examples.
RecommendBatch	RecommendBatchPoints	RecommendBatchResponse	Look for the points which are closer to stored positive examples and at the same time further to negative examples.
RecommendGroups	RecommendPointGroups	RecommendGroupsResponse	Look for the points which are closer to stored positive examples and at the same time further to negative examples, grouped by a given field
Count	CountPoints	CountResponse	Count points in collection with given filtering conditions
UpdateBatch	UpdateBatchPoints	UpdateBatchResponse	Perform multiple update operations in one request

Top

qdrant.proto

HealthCheckReply

Field	Type	Label	Description
title	string
version	string

HealthCheckRequest

Qdrant

Method Name	Request Type	Response Type	Description
HealthCheck	HealthCheckRequest	HealthCheckReply

Top

qdrant_internal_service.proto

HttpPortRequest

HttpPortResponse

Field	Type	Label	Description
port	int32

QdrantInternal

Method Name	Request Type	Response Type	Description
GetHttpPort	HttpPortRequest	HttpPortResponse	Get HTTP port for remote host.

Top

snapshots_service.proto

CreateFullSnapshotRequest

CreateSnapshotRequest

Field	Type	Label	Description
collection_name	string		Name of the collection

CreateSnapshotResponse

Field	Type	Label	Description
snapshot_description	SnapshotDescription
time	double		Time spent to process

DeleteFullSnapshotRequest

Field	Type	Label	Description
snapshot_name	string		Name of the full snapshot

DeleteSnapshotRequest

Field	Type	Label	Description
collection_name	string		Name of the collection
snapshot_name	string		Name of the collection snapshot

DeleteSnapshotResponse

Field	Type	Label	Description
time	double		Time spent to process

ListFullSnapshotsRequest

ListSnapshotsRequest

Field	Type	Label	Description
collection_name	string		Name of the collection

ListSnapshotsResponse

Field	Type	Label	Description
snapshot_descriptions	SnapshotDescription	repeated
time	double		Time spent to process

SnapshotDescription

Field	Type	Label	Description
name	string		Name of the snapshot
creation_time	google.protobuf.Timestamp		Creation time of the snapshot
size	int64		Size of the snapshot in bytes

Snapshots

Method Name	Request Type	Response Type	Description
Create	CreateSnapshotRequest	CreateSnapshotResponse	Create collection snapshot
List	ListSnapshotsRequest	ListSnapshotsResponse	List collection snapshots
Delete	DeleteSnapshotRequest	DeleteSnapshotResponse	Delete collection snapshots
CreateFull	CreateFullSnapshotRequest	CreateSnapshotResponse	Create full storage snapshot
ListFull	ListFullSnapshotsRequest	ListSnapshotsResponse	List full storage snapshots
DeleteFull	DeleteFullSnapshotRequest	DeleteSnapshotResponse	List full storage snapshots

Scalar Value Types

.proto Type	Notes	C++	Java	Python	Go	C#	PHP	Ruby
double		double	double	float	float64	double	float	Float
float		float	float	float	float32	float	float	Float
int32	Uses variable-length encoding. Inefficient for encoding negative numbers – if your field is likely to have negative values, use sint32 instead.	int32	int	int	int32	int	integer	Bignum or Fixnum (as required)
int64	Uses variable-length encoding. Inefficient for encoding negative numbers – if your field is likely to have negative values, use sint64 instead.	int64	long	int/long	int64	long	integer/string	Bignum
uint32	Uses variable-length encoding.	uint32	int	int/long	uint32	uint	integer	Bignum or Fixnum (as required)
uint64	Uses variable-length encoding.	uint64	long	int/long	uint64	ulong	integer/string	Bignum or Fixnum (as required)
sint32	Uses variable-length encoding. Signed int value. These more efficiently encode negative numbers than regular int32s.	int32	int	int	int32	int	integer	Bignum or Fixnum (as required)
sint64	Uses variable-length encoding. Signed int value. These more efficiently encode negative numbers than regular int64s.	int64	long	int/long	int64	long	integer/string	Bignum
fixed32	Always four bytes. More efficient than uint32 if values are often greater than 2^28.	uint32	int	int	uint32	uint	integer	Bignum or Fixnum (as required)
fixed64	Always eight bytes. More efficient than uint64 if values are often greater than 2^56.	uint64	long	int/long	uint64	ulong	integer/string	Bignum
sfixed32	Always four bytes.	int32	int	int	int32	int	integer	Bignum or Fixnum (as required)
sfixed64	Always eight bytes.	int64	long	int/long	int64	long	integer/string	Bignum
bool		bool	boolean	boolean	bool	bool	boolean	TrueClass/FalseClass
string	A string must always contain UTF-8 encoded or 7-bit ASCII text.	string	String	str/unicode	string	string	string	String (UTF-8)
bytes	May contain any arbitrary sequence of bytes.	string	ByteString	str	[]byte	ByteString	string	String (ASCII-8BIT)